CN105183714A - Sentence similarity calculation method and apparatus - Google Patents
Sentence similarity calculation method and apparatus Download PDFInfo
- Publication number
- CN105183714A CN105183714A CN201510536882.8A CN201510536882A CN105183714A CN 105183714 A CN105183714 A CN 105183714A CN 201510536882 A CN201510536882 A CN 201510536882A CN 105183714 A CN105183714 A CN 105183714A
- Authority
- CN
- China
- Prior art keywords
- sentences
- word
- similarity
- cos distance
- vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The present invention discloses a sentence similarity calculation method and apparatus and relates to the technical field of automatic correcting. The method comprises: acquiring a vector corresponding to each word; performing syntax analysis on two sentences to be compared so as to acquire words forming compositions of the two sentences; calculating a first cosine distance between the vectors corresponding to the words forming the corresponding compositions of the two sentences; and according to the first cosine distance, determining similarity between the two sentences. According to the method provided by the present invention, by performing syntax analysis on the sentences and structurally holding semantics of the sentences, similarity between the sentences are more accurately calculated; and in addition, the word vectors based on a neural network model are adopted to represent the words, thereby more accurately calculating similarity between the words and getting rid of restrictions of a near-synonym dictionary.
Description
Technical field
The present invention relates to and automatically correct technical field, particularly a kind of sentence similarity computing method and device.
Background technology
In english composition is corrected automatically, a key factor is had to be the degree pertinent to the point calculating composition.Existing technical method mainly carries out the coupling of English character by the composition topic sentence of each section and the exercise question of composition, occur identical English character number reflect the size of the degree of approximation of topic sentence and exercise question, thus reflect composition and to keep to the point the size of degree.But add up identical English character and do not have generality, same semanteme can be expressed with different words, and therefore more the method in forward position sets up near synonym table now, mates in conjunction with near synonym table.
But in prior art, the coupling between sentence is that the word that isolated word regarded as in sentence is carried out mating, and do not consider sentence structure, this causes the assurance of the semanteme to sentence inaccurate.Such as: english sentence " Mymotherhasacatwithfourlegs. " (sentence 1) and " Mymotherhasfourlegs. " (sentence 2).If do not consider sentence structure, compare from isolated word, two sentences only differ from two important words " with " and " cat ", but from actual semanteme, two sentences differ greatly, and cause sentence similarity accuracy rate too low.
Summary of the invention
For improving the accuracy rate calculating sentence similarity, the invention provides a kind of sentence similarity computing method, described method comprises:
Obtain the vector that each word is corresponding;
Syntactic analysis is carried out to be compared two sentences, to obtain the word forming each composition in described two sentences;
Calculate the first COS distance between the corresponding vector of the word forming corresponding composition in described two sentences;
The similarity between described two sentences is determined according to described first COS distance.
Wherein, the vector that each word of described acquisition is corresponding, comprises further:
Natural language language material is trained by term vector instrument, to obtain vector corresponding to each word.
Wherein, described natural language language material to be trained by term vector instrument, comprises further:
By term vector instrument, the training of three-layer neural network model is adopted to natural language language material.
Wherein, described syntactic analysis is carried out to be compared two sentences, to obtain the word that described two sentences form each composition, comprises further:
Carry out syntactic analysis to described two sentences, to obtain the syntax tree of described two sentences, described syntax tree comprises in sentence the word forming each composition.
Wherein, the described similarity determining between described two sentences according to described first COS distance, comprises further:
Described first COS distance is weighted on average, to obtain the second COS distance, using described second COS distance as the similarity between described two sentences.
The invention also discloses a kind of sentence similarity calculation element, described device comprises:
Vector acquiring unit, for obtaining vector corresponding to each word;
Syntactic analysis unit, for carrying out syntactic analysis to be compared two sentences, to obtain the word forming each composition in described two sentences;
Metrics calculation unit, for calculating the first COS distance between the corresponding vector of the word forming corresponding composition in described two sentences;
Similarity determining unit, for determining the similarity between described two sentences according to described first COS distance.
Wherein, described vectorial acquiring unit, is further used for being trained by term vector instrument natural language language material, to obtain vector corresponding to each word.
Wherein, described vectorial acquiring unit, is further used for adopting the training of three-layer neural network model to natural language language material by term vector instrument.
Wherein, described syntactic analysis unit, be further used for carrying out syntactic analysis to described two sentences, to obtain the syntax tree of described two sentences, described syntax tree comprises in sentence the word forming each composition.
Wherein, described similarity determining unit, is further used for described first COS distance to be weighted on average, to obtain the second COS distance, using described second COS distance as the similarity between described two sentences.
The present invention is by carrying out syntactic analysis to sentence, the semanteme of sentence is held from configuration aspects, thus the degree of approximation calculated more exactly between sentence, in addition, the term vector that have employed based on neural network model represents word, thus the degree of approximation more accurately calculated between word, and break away from the restriction of near synonym dictionary.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the sentence similarity computing method of one embodiment of the present invention;
Fig. 2 is the structural representation of the syntax tree of two English sentences;
Fig. 3 is the structured flowchart of the sentence similarity calculation element of one embodiment of the present invention.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples for illustration of the present invention, but are not used for limiting the scope of the invention.
Fig. 1 is the process flow diagram of the sentence similarity computing method of one embodiment of the present invention; With reference to Fig. 1, described method comprises:
S101: obtain the vector that each word is corresponding;
In the prior art, the foundation of near synonym table is carry out manual arrangement by dictionary substantially, workload is large, and there is the wideless problem of coverage rate, degree of approximation between word is also difficult to quantize, for overcoming this problem, and the vector that each word of quick obtaining is corresponding, thus the COS distance between being convenient to by the corresponding vector of word reflects the degree of approximation between word, in present embodiment, can be trained, to obtain vector corresponding to each word by term vector instrument (such as: the instruments such as word2vec) natural language language material.
After training after training, each word can represent (being generally 50 dimensions) with a vector, and the degree of approximation between two words is weighed by the COS distance between the vector of correspondence.COS distance is less, represents two word degrees of approximation less; COS distance is larger, represents two word degrees of approximation larger.
In order to ensure the accuracy of the vector that word is corresponding, described term vector instrument can adopt the training of three-layer neural network model, and certainly, also can adopt other model training, present embodiment is not limited this.
S102: carry out syntactic analysis to be compared two sentences, to obtain the word forming each composition in described two sentences;
For ease of comparing this two sentences, syntactic analysis can be carried out to described two sentences, to obtain the syntax tree of described two sentences, described syntax tree comprises in sentence the word forming each composition (i.e. the composition such as subject, predicate, object, subordinate clause), with reference to Fig. 2, for english sentence " Mymotherhasacatwithfourlegs " (sentence 1) and " Mymotherhasfourlegs " (sentence 2) known;
The word forming each composition in sentence 1 is: the word of composition subject (SBJ) is mymother, the word of composition predicate (VB) is has, the word of composition object (OBJ) is acat, and the word of object complement (NC) is fourlegs;
The word forming each composition in sentence 2 is: the word of composition subject (SBJ) is mymother, and the word of composition predicate (VB) is has, and the word of composition object (OBJ) is fourlegs.
S103: calculate the first COS distance between the corresponding vector of the word forming corresponding composition in described two sentences;
It should be noted that, when calculating the first COS distance, the word for identical component is needed to calculate, for above-mentioned two sentences, the first COS distance then between the corresponding vector of the word of the composition subject of calculating two sentences, the first COS distance between the corresponding vector of word of composition predicate, and the first COS distance between the corresponding vector of the word of composition object.
S104: determine the similarity between described two sentences according to described first COS distance.
In specific implementation, after obtaining each first COS distance, the similarity between described two sentences can be determined, but in order to improve the correctness of similarity further, in present embodiment, described first COS distance is weighted on average, to obtain the second COS distance, using described second COS distance as the similarity between described two sentences, certainly, when calculating the second COS distance, also can adopt other modes, such as, not consider weighting, directly be averaged calculating, and present embodiment is not limited this.
Will be understood that, described second COS distance can weigh the degree of approximation between two sentences, and the second COS distance is less, then represent degree of approximation between two sentences less; Second COS distance is larger, then represent degree of approximation between two sentences larger.
Present embodiment is by carrying out syntactic analysis to sentence, the semanteme of sentence is held from configuration aspects, thus the degree of approximation calculated more exactly between sentence, in addition, the term vector that have employed based on neural network model represents word, thus the degree of approximation more accurately calculated between word, and break away from the restriction of near synonym dictionary.
Fig. 3 is the structured flowchart of the sentence similarity calculation element of one embodiment of the present invention; With reference to Fig. 3, described device comprises:
Vector acquiring unit 301, for obtaining vector corresponding to each word;
Syntactic analysis unit 302, for carrying out syntactic analysis to be compared two sentences, to obtain the word forming each composition in described two sentences;
Metrics calculation unit 303, for calculating the first COS distance between the corresponding vector of the word forming corresponding composition in described two sentences;
Similarity determining unit 304, for determining the similarity between described two sentences according to described first COS distance.
Alternatively, described vectorial acquiring unit, is further used for being trained by term vector instrument natural language language material, to obtain vector corresponding to each word.
Alternatively, described vectorial acquiring unit, is further used for adopting the training of three-layer neural network model to natural language language material by term vector instrument.
Alternatively, described syntactic analysis unit, be further used for carrying out syntactic analysis to described two sentences, to obtain the syntax tree of described two sentences, described syntax tree comprises in sentence the word forming each composition.
Alternatively, described similarity determining unit, is further used for described first COS distance to be weighted on average, to obtain the second COS distance, using described second COS distance as the similarity between described two sentences.
Above embodiment is only for illustration of the present invention; and be not limitation of the present invention; the those of ordinary skill of relevant technical field; without departing from the spirit and scope of the present invention; can also make a variety of changes and modification; therefore all equivalent technical schemes also belong to category of the present invention, and scope of patent protection of the present invention should be defined by the claims.
Claims (10)
1. sentence similarity computing method, is characterized in that, described method comprises:
Obtain the vector that each word is corresponding;
Syntactic analysis is carried out to be compared two sentences, to obtain the word forming each composition in described two sentences;
Calculate the first COS distance between the corresponding vector of the word forming corresponding composition in described two sentences;
The similarity between described two sentences is determined according to described first COS distance.
2. the method for claim 1, is characterized in that, the vector that each word of described acquisition is corresponding, comprises further:
Natural language language material is trained by term vector instrument, to obtain vector corresponding to each word.
3. method as claimed in claim 2, is characterized in that, is describedly trained by term vector instrument natural language language material, comprises further:
By term vector instrument, the training of three-layer neural network model is adopted to natural language language material.
4. the method according to any one of claims 1 to 3, is characterized in that, describedly carries out syntactic analysis to be compared two sentences, to obtain the word that described two sentences form each composition, comprises further:
Carry out syntactic analysis to described two sentences, to obtain the syntax tree of described two sentences, described syntax tree comprises in sentence the word forming each composition.
5. the method according to any one of claims 1 to 3, is characterized in that, the described similarity determining between described two sentences according to described first COS distance, comprises further:
Described first COS distance is weighted on average, to obtain the second COS distance, using described second COS distance as the similarity between described two sentences.
6. a sentence similarity calculation element, is characterized in that, described device comprises:
Vector acquiring unit, for obtaining vector corresponding to each word;
Syntactic analysis unit, for carrying out syntactic analysis to be compared two sentences, to obtain the word forming each composition in described two sentences;
Metrics calculation unit, for calculating the first COS distance between the corresponding vector of the word forming corresponding composition in described two sentences;
Similarity determining unit, for determining the similarity between described two sentences according to described first COS distance.
7. device as claimed in claim 6, be is characterized in that, described vectorial acquiring unit, is further used for being trained by term vector instrument natural language language material, to obtain vector corresponding to each word.
8. device as claimed in claim 7, is characterized in that, described vectorial acquiring unit, is further used for adopting the training of three-layer neural network model to natural language language material by term vector instrument.
9. the device according to any one of claim 6 ~ 8, it is characterized in that, described syntactic analysis unit, be further used for carrying out syntactic analysis to described two sentences, to obtain the syntax tree of described two sentences, described syntax tree comprises in sentence the word forming each composition.
10. the device according to any one of claim 6 ~ 8, it is characterized in that, described similarity determining unit, be further used for described first COS distance to be weighted on average, to obtain the second COS distance, using described second COS distance as the similarity between described two sentences.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510536882.8A CN105183714A (en) | 2015-08-27 | 2015-08-27 | Sentence similarity calculation method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510536882.8A CN105183714A (en) | 2015-08-27 | 2015-08-27 | Sentence similarity calculation method and apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105183714A true CN105183714A (en) | 2015-12-23 |
Family
ID=54905803
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510536882.8A Pending CN105183714A (en) | 2015-08-27 | 2015-08-27 | Sentence similarity calculation method and apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105183714A (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105653671A (en) * | 2015-12-29 | 2016-06-08 | 畅捷通信息技术股份有限公司 | Similar information recommendation method and system |
CN105930413A (en) * | 2016-04-18 | 2016-09-07 | 北京百度网讯科技有限公司 | Training method for similarity model parameters, search processing method and corresponding apparatuses |
CN106021223A (en) * | 2016-05-09 | 2016-10-12 | Tcl集团股份有限公司 | Sentence similarity calculation method and system |
CN106202395A (en) * | 2016-07-11 | 2016-12-07 | 上海智臻智能网络科技股份有限公司 | Text clustering method and device |
CN107730002A (en) * | 2017-10-13 | 2018-02-23 | 国网湖南省电力公司 | A kind of communication network shutdown remote control parameter intelligent fuzzy comparison method |
CN107844608A (en) * | 2017-12-06 | 2018-03-27 | 湖南大学 | A kind of sentence similarity comparative approach based on term vector |
CN108268441A (en) * | 2017-01-04 | 2018-07-10 | 科大讯飞股份有限公司 | Sentence similarity computational methods and apparatus and system |
WO2018153217A1 (en) * | 2017-02-27 | 2018-08-30 | 芋头科技(杭州)有限公司 | Method for determining sentence similarity |
CN109117474A (en) * | 2018-06-25 | 2019-01-01 | 广州多益网络股份有限公司 | Calculation method, device and the storage medium of statement similarity |
CN109492213A (en) * | 2017-09-11 | 2019-03-19 | 阿里巴巴集团控股有限公司 | Sentence similarity calculation method and device |
CN109766547A (en) * | 2018-12-26 | 2019-05-17 | 重庆邮电大学 | A kind of sentence similarity calculation method |
CN109871437A (en) * | 2018-11-30 | 2019-06-11 | 阿里巴巴集团控股有限公司 | Method and device for the processing of customer problem sentence |
CN110309263A (en) * | 2019-06-06 | 2019-10-08 | 中国人民解放军军事科学院军事科学信息研究中心 | A kind of semantic-based working attributes content of text judgement method for confliction detection and device |
CN111414765A (en) * | 2020-03-20 | 2020-07-14 | 北京百度网讯科技有限公司 | Sentence consistency determination method and device, electronic equipment and readable storage medium |
US10922486B2 (en) | 2019-03-13 | 2021-02-16 | International Business Machines Corporation | Parse tree based vectorization for natural language processing |
US20210209311A1 (en) * | 2018-11-28 | 2021-07-08 | Ping An Technology (Shenzhen) Co., Ltd. | Sentence distance mapping method and apparatus based on machine learning and computer device |
CN113392630A (en) * | 2021-07-01 | 2021-09-14 | 浙江工业大学 | Semantic analysis-based Chinese sentence similarity calculation method and system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1741012A (en) * | 2004-08-23 | 2006-03-01 | 富士施乐株式会社 | Test search apparatus and method |
US20090204605A1 (en) * | 2008-02-07 | 2009-08-13 | Nec Laboratories America, Inc. | Semantic Search Via Role Labeling |
CN103218432A (en) * | 2013-04-15 | 2013-07-24 | 北京邮电大学 | Named entity recognition-based news search result similarity calculation method |
CN104375989A (en) * | 2014-12-01 | 2015-02-25 | 国家电网公司 | Natural language text keyword association network construction system |
CN104391963A (en) * | 2014-12-01 | 2015-03-04 | 北京中科创益科技有限公司 | Method for constructing correlation networks of keywords of natural language texts |
-
2015
- 2015-08-27 CN CN201510536882.8A patent/CN105183714A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1741012A (en) * | 2004-08-23 | 2006-03-01 | 富士施乐株式会社 | Test search apparatus and method |
US20090204605A1 (en) * | 2008-02-07 | 2009-08-13 | Nec Laboratories America, Inc. | Semantic Search Via Role Labeling |
CN103218432A (en) * | 2013-04-15 | 2013-07-24 | 北京邮电大学 | Named entity recognition-based news search result similarity calculation method |
CN104375989A (en) * | 2014-12-01 | 2015-02-25 | 国家电网公司 | Natural language text keyword association network construction system |
CN104391963A (en) * | 2014-12-01 | 2015-03-04 | 北京中科创益科技有限公司 | Method for constructing correlation networks of keywords of natural language texts |
Non-Patent Citations (3)
Title |
---|
王庆林,张九天: "《气候变化领域本体手册》", 1 May 2015, 北京理工大学出版社 * |
郑诚,夏青松,孙昌年: "一种基于成分的句子相似度计算", 《计算机技术与发展》 * |
马刚: "《基于语义的Web数据挖掘》", 31 January 2014, 东北财经大学出版社 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105653671A (en) * | 2015-12-29 | 2016-06-08 | 畅捷通信息技术股份有限公司 | Similar information recommendation method and system |
CN105930413A (en) * | 2016-04-18 | 2016-09-07 | 北京百度网讯科技有限公司 | Training method for similarity model parameters, search processing method and corresponding apparatuses |
CN106021223A (en) * | 2016-05-09 | 2016-10-12 | Tcl集团股份有限公司 | Sentence similarity calculation method and system |
CN106021223B (en) * | 2016-05-09 | 2020-06-23 | Tcl科技集团股份有限公司 | Sentence similarity calculation method and system |
CN106202395A (en) * | 2016-07-11 | 2016-12-07 | 上海智臻智能网络科技股份有限公司 | Text clustering method and device |
CN106202395B (en) * | 2016-07-11 | 2019-12-31 | 上海智臻智能网络科技股份有限公司 | Text clustering method and device |
CN108268441B (en) * | 2017-01-04 | 2021-06-22 | 科大讯飞股份有限公司 | Sentence similarity calculation method, device and system |
CN108268441A (en) * | 2017-01-04 | 2018-07-10 | 科大讯飞股份有限公司 | Sentence similarity computational methods and apparatus and system |
CN108509408A (en) * | 2017-02-27 | 2018-09-07 | 芋头科技(杭州)有限公司 | A kind of sentence similarity judgment method |
US10949709B2 (en) | 2017-02-27 | 2021-03-16 | Yutou Technology (Hangzhou) Co., Ltd. | Method for determining sentence similarity |
CN108509408B (en) * | 2017-02-27 | 2019-11-22 | 芋头科技(杭州)有限公司 | A kind of sentence similarity judgment method |
WO2018153217A1 (en) * | 2017-02-27 | 2018-08-30 | 芋头科技(杭州)有限公司 | Method for determining sentence similarity |
CN109492213A (en) * | 2017-09-11 | 2019-03-19 | 阿里巴巴集团控股有限公司 | Sentence similarity calculation method and device |
CN107730002B (en) * | 2017-10-13 | 2020-06-02 | 国网湖南省电力公司 | Intelligent fuzzy comparison method for remote control parameters of communication gateway machine |
CN107730002A (en) * | 2017-10-13 | 2018-02-23 | 国网湖南省电力公司 | A kind of communication network shutdown remote control parameter intelligent fuzzy comparison method |
CN107844608B (en) * | 2017-12-06 | 2021-11-30 | 湖南大学 | Sentence similarity comparison method based on word vectors |
CN107844608A (en) * | 2017-12-06 | 2018-03-27 | 湖南大学 | A kind of sentence similarity comparative approach based on term vector |
CN109117474A (en) * | 2018-06-25 | 2019-01-01 | 广州多益网络股份有限公司 | Calculation method, device and the storage medium of statement similarity |
US20210209311A1 (en) * | 2018-11-28 | 2021-07-08 | Ping An Technology (Shenzhen) Co., Ltd. | Sentence distance mapping method and apparatus based on machine learning and computer device |
CN109871437A (en) * | 2018-11-30 | 2019-06-11 | 阿里巴巴集团控股有限公司 | Method and device for the processing of customer problem sentence |
CN109871437B (en) * | 2018-11-30 | 2023-04-21 | 阿里巴巴集团控股有限公司 | Method and device for processing user problem statement |
CN109766547A (en) * | 2018-12-26 | 2019-05-17 | 重庆邮电大学 | A kind of sentence similarity calculation method |
CN109766547B (en) * | 2018-12-26 | 2022-10-18 | 重庆邮电大学 | Sentence similarity calculation method |
US10922486B2 (en) | 2019-03-13 | 2021-02-16 | International Business Machines Corporation | Parse tree based vectorization for natural language processing |
CN110309263A (en) * | 2019-06-06 | 2019-10-08 | 中国人民解放军军事科学院军事科学信息研究中心 | A kind of semantic-based working attributes content of text judgement method for confliction detection and device |
CN111414765A (en) * | 2020-03-20 | 2020-07-14 | 北京百度网讯科技有限公司 | Sentence consistency determination method and device, electronic equipment and readable storage medium |
CN113392630A (en) * | 2021-07-01 | 2021-09-14 | 浙江工业大学 | Semantic analysis-based Chinese sentence similarity calculation method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105183714A (en) | Sentence similarity calculation method and apparatus | |
CN103885938A (en) | Industry spelling mistake checking method based on user feedback | |
CN104731774B (en) | Towards the personalized interpretation method and device of general machine translation engine | |
CN107169079A (en) | A kind of field text knowledge abstracting method based on Deepdive | |
CN105843801A (en) | Multi-translation parallel corpus construction system | |
CN102567306B (en) | Acquisition method and acquisition system for similarity of vocabularies between different languages | |
CN102023921A (en) | Automatic grading method and device of structured query language (SQL) program | |
CN106339371B (en) | A kind of English-Chinese meaning of a word mapping method and device based on term vector | |
CN103106189A (en) | Method and device for excavating synonymous attribute words | |
CN107239574A (en) | A kind of method and device of intelligent Answer System knowledge problem matching | |
CN105930319A (en) | Methods and devices for establishing question knowledge point obtaining model and obtaining question knowledge point | |
CN108304317A (en) | A kind of single process procedures static slicing method and system executing frequency based on path | |
CN108153730A (en) | A kind of polysemant term vector training method and device | |
CN108959630A (en) | A kind of character attribute abstracting method towards English without structure text | |
CN118035280A (en) | Data query method, device, electronic equipment and storage medium | |
CN105243053A (en) | Method and apparatus for extracting key sentence of document | |
CN104699595A (en) | Software testing method facing to software upgrading | |
CN104298657A (en) | Evaluation index analysis system based on expression | |
Munk et al. | Detecting errors in machine translation using residuals and metrics of automatic evaluation | |
CN114936271A (en) | Method, apparatus and medium for natural language translation database query | |
CN109783775A (en) | Method and system for marking content of user corpus | |
CN112799938A (en) | Automatic evaluation method and system for microbit programming questions based on python | |
Song | Phraseological analysis of learner corpus based on language model | |
Mahlaza et al. | Measuring verb similarity using binary coefficients with application to isiXhosa and isiZulu | |
CN110889273A (en) | Data processing method, data processing apparatus, storage medium, and electronic device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151223 |
|
RJ01 | Rejection of invention patent application after publication |